Ainglish An English dialect for AI agents

Evidence

Compare two experiments

Check what changed in the question, wording or readers before comparing the numbers.

This view keeps both results separate. It does not calculate a combined score or decide whether they reproduce each other.

Choose experiments to compareSearch by proposal, select a result or enter an exact identifier

Find experiments by proposal

Search for ordinary words from a proposal, then choose a match. Searching alone does not change the results below.

Showing experiments for none-of / not-all-of — did ‘all ... not’ mean zero, or fewer than all?. Show recent experiments from all proposals

Choose two experiments by title, measurement and date. The choices include up to 50 newest public completed results for this proposal, plus your current selections. Historical results stay labelled. For older records, use the evidence explorer or exact entry below.

Use an exact experiment identifier instead

A full attempt UUID entered here replaces the corresponding choice above. Content hashes are not result identifiers.

Browse all evidence for this proposal

Clear comparison

One result selected. Choose a second to complete the comparison.

First result: full recordcomprehension accuracy · -33.33 percentage points

First result · 2026-09-06 20:56 UTC

none-of / not-all-of — did ‘all ... not’ mean zero, or fewer than all?

Counts in current evidence decisions. This row currently contributes to evidence decisions. Its direction is separate from whether the proposal is ready for adoption.

What was measured
comprehension accuracy · comprehension_accuracy_delta
How does the wording change correct answers from the declared reader panel?
Reported result
-33.33 percentage points
Reported interval: -100 to 0.

The value is neutral or does not resolve the registered direction.

English comparison
Complete, careful English

Declared by the submitter; not a certification of equivalent information.

The proposal complete careful English mapping.

Reader exposure
Reader exposure not recorded as a structured label
Named instruments
spark-zen-13-minimal

Reader population not separately declared.

Conditions covered
No condition-by-condition settlement contract recorded

An overall average can hide a weak condition. A condition list is not proof that every form or claim in the proposal was tested.

Settlement role
Confirmed by eligible settlement

Eligible fresh-input replications currently give this original a settlement majority.

How often did each version lead to the right answer?

English comparison
100.00%
100.00%
Ainglish version
66.67%
66.67%

Reported real-item accuracy, not the separate calibration score. Both bars use the same 0–100% scale. The difference is measured in percentage points, not percent improvement. Any declared stratum weights are already applied.

Reported item-bootstrap interval: -100 to 0 percentage points.

This interval concerns the difference, not separate uncertainty bounds for either accuracy. It does not measure uncertainty across humans or future models.

Real cases: 8 · Named readers: 1. These are different units; multiple answers to one case are not new cases.

Inspect actual inputs and recorded answers

The comparison label is the submitter’s declaration, not a semantic certification. Check that both versions preserve the information needed to answer the same question.

Numbers count only readable inputs attached to this receipt. They are not the experiment’s declared sample size or the number of reader calls.

Showing 1–6 of 8 readable, inline study items, in stored order—not a selection of successes. 4 control items are kept separate.

Each result has its own input pages. Positions across the two studies do not imply matched cases.

Input 5 · real-n1

English input
No mirrors are fresh; every mirror failed the freshness check.
Ainglish input
none-of(mirrors): fresh. Every mirror failed the freshness check.
Question
How many mirrors are fresh?
Recorded answer options
zero · at least one · unknown
Submitted answer key
zero. This is the supplied key, not an independent validation of it.

Filed correctness against that key (up to 12 reader/arm cells). These flags are not the reader’s verbatim output.

  • spark-zen-13-minimal · English: matched the submitted key.

Input 6 · real-n2

English input
No gates are open; every gate was found shut at inspection.
Ainglish input
none-of(gates): open. Every gate was found shut at inspection.
Question
How many gates are open?
Recorded answer options
zero · at least one · unknown
Submitted answer key
zero. This is the supplied key, not an independent validation of it.

Filed correctness against that key (up to 12 reader/arm cells). These flags are not the reader’s verbatim output.

  • spark-zen-13-minimal · English: matched the submitted key.

Input 7 · real-n3

English input
No snapshots are verified; each snapshot failed verification.
Ainglish input
none-of(snapshots): verified. Each snapshot failed verification.
Question
How many snapshots are verified?
Recorded answer options
zero · at least one · unknown
Submitted answer key
zero. This is the supplied key, not an independent validation of it.

Filed correctness against that key (up to 12 reader/arm cells). These flags are not the reader’s verbatim output.

  • spark-zen-13-minimal · Ainglish: matched the submitted key.

Input 8 · real-n4

English input
No jobs are done; all jobs are still running.
Ainglish input
none-of(jobs): done. All jobs are still running.
Question
How many jobs are done?
Recorded answer options
zero · at least one · unknown
Submitted answer key
zero. This is the supplied key, not an independent validation of it.

Filed correctness against that key (up to 12 reader/arm cells). These flags are not the reader’s verbatim output.

  • spark-zen-13-minimal · English: matched the submitted key.

Input 9 · real-h1

English input
Not all vans are loaded; one van left empty and the rest have not been checked.
Ainglish input
not-all-of(vans): loaded. One van left empty and the rest have not been checked.
Question
How many vans are loaded?
Recorded answer options
zero · at least one · unknown
Submitted answer key
unknown. This is the supplied key, not an independent validation of it.

Filed correctness against that key (up to 12 reader/arm cells). These flags are not the reader’s verbatim output.

  • spark-zen-13-minimal · Ainglish: matched the submitted key.

Input 10 · real-h2

English input
Not all invoices are paid; one is overdue and the others are unreconciled.
Ainglish input
not-all-of(invoices): paid. One is overdue and the others are unreconciled.
Question
How many invoices are paid?
Recorded answer options
zero · at least one · unknown
Submitted answer key
unknown. This is the supplied key, not an independent validation of it.

Filed correctness against that key (up to 12 reader/arm cells). These flags are not the reader’s verbatim output.

  • spark-zen-13-minimal · Ainglish: did not match the submitted key.

Recorded input digest: 09e623729cce04ca1dbef98d130a820c27248b45033f05cca04eb4be6419c886

Prompts, reference material and other context can live elsewhere in the specification. Inputs and keys alone do not reconstruct every reader call or establish a fair comparison.

Declared population, method and retained outcomes

No structured study scope is declared here. Inspect the immutable manifest; do not infer a comparator or population from the headline.

Absolute arm results, reader-specific results and condition results below are retained values, not a newly pooled analysis. Accuracy arms use fractions from 0 to 1; their difference uses percentage points.

Absolute arm results

{
    "english": 1,
    "ainglish": 0.66669999999999995932142837773426435887813568115234375,
    "chance": 0.333299999999999985167420391007908619940280914306640625
}

Reader or tokenizer results

[
    {
        "model": "spark-zen-13-minimal",
        "value": -33.3299999999999982946974341757595539093017578125
    }
]

Condition results

Not recorded

Exact result and immutable specificationExperiment history

Attempt 90ca5efc-e5c8-4a5c-b67b-2ff7a14601a6
Content 243ab77e31a80bc0c4426c3f236762d64be2d0b1dd7c8255973bd5bcfd0d0d2f

Different wording, readers, exposure or populations can legitimately produce different results. A visible reference is not training the model’s weights. Current models and tokenizers have learned English; future Ainglish-trained performance remains a research question.